Power LangChain with
the best open-source models
Use Kyma as the model provider for your LangChain chains and agents. Just point ChatOpenAI at Kyma — active models, auto-failover, free to start. No OpenAI or Anthropic key needed.
Best Open Models
Qwen 3.6 Plus for quality, Kimi K2.6 for agents and tools, DeepSeek V4 Flash for value — pick any model with a single string change in ChatOpenAI.
Auto-Failover
Multi-route redundancy behind one endpoint. If a route is slow, Kyma switches automatically — your chains and agents keep running.
OpenAI-Compatible
LangChain's ChatOpenAI class talks to any OpenAI-compatible endpoint. Set the base URL to Kyma and everything else stays the same.
Recommended Models for LangChain
Ranked by quality, context length, tool support, and cost for real LangChain workloads.
Alibaba's flagship and the highest-quality all-rounder. 131K context with strong reasoning. The default choice for most LangChain chains and agents.
qwen-3.6-plus131K context
Moonshot's newest. Best agentic tool use with a 262K context window — ideal for LangChain agents, tool calling, and long-horizon workflows.
kimi-k2.6262K context
DeepSeek's 284B MoE with a 1M context window. Fast and cheap with strong reasoning — the best quality-per-dollar for high-volume chains.
deepseek-v4-flash1M context
Google's open multimodal model. Lowest cost per token and supports image input — great for cheap vision tasks inside LangChain.
gemma-4-31bLowest cost
Alibaba's purpose-built code model. Strong on generation and debugging — pair it with LangChain code chains and tools.
qwen-3-coderCode-tuned
Setup in 30 Seconds
1. Get your free API key → 2. Point ChatOpenAI at Kyma → 3. Run your LangChain app.
# pip install langchain-openai
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(
model="qwen-3.6-plus",
base_url="https://kymaapi.com/v1",
api_key="ky-xxxxx", # get yours at kymaapi.com
)
resp = llm.invoke("Explain LangChain in one sentence.")
print(resp.content)// npm install @langchain/openai
import { ChatOpenAI } from "@langchain/openai";
const llm = new ChatOpenAI({
model: "qwen-3.6-plus",
apiKey: "ky-xxxxx", // get yours at kymaapi.com
configuration: {
baseURL: "https://kymaapi.com/v1",
},
});
const resp = await llm.invoke("Explain LangChain in one sentence.");
console.log(resp.content);Pro Tips
Pick the right model for each chain to get the best results and lowest cost.
Use kimi-k2.6 for LangChain agents and tool-calling workflows that need long context
Use deepseek-v4-flash for high-volume chains where value and a 1M context window matter
Use gemma-4-31b to cut costs on simple prompts and cheap vision tasks
Build with LangChain — free
$0.50 free credits on signup. No credit card required.
Get Free API KeyExplore more
Browse the recommended models for LangChain and compare them against the rest of the catalog.